Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Long-horizon Agentic Task Completion on Odysseys

34Average Success Rate (%)

MACU

7.4814.36521.2528.135Jun 1, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.06
3425.5110.3-52.1
2026.06
3223.5116.3-46.1
2026.06
8.5-162.4-